Create lid201-model.bin
Browse files"An Open Dataset and Model for Language Identification" (Burchell et al., ACL 2023).
The OpenLID fasttext LID model can be found at https://data.statmt.org/lid/lid201-model.bin.gz. To use it, install FastText, decompress the model, then run fasttext predict lid201-model.bin $DATA > output.fasttext.
The model is licensed under the GNU General Public License v3.0.
This is the unquantized, original model.
The quantized model is available from this repository under quantized/
original/lid201-model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e2bc6d0d3048b38c4e2e8aa77b4618108670eb91cb72544d3340f605964a78b
|
| 3 |
+
size 1233956788
|